Erin Jospe, MD
To support integrated care teams, organizations need to look at where there are gaps appropriate for technology to fill
As health care organizations seek to deliver the highest quality of care to their communities while containing health care costs in the process, coordinating patient care effectively across the continuum is more crucial than ever. The mix of providers involved in a given patient’s care has grown as medicine has become increasingly specialized. As providers, we have an obligation to understand what each episode of care offers the patient and to ensure those episodes are not viewed in isolation, but rather as part of an arcing narrative with the patient at its center.
And yet, given the overwhelming demands on our time, how can we as providers gain a true sense of the other potential contributors to our patients’ care? And how can we begin to collaborate around that care when we don’t always know or have an effective means of communicating with the other providers on a given care team? When deployed correctly, these are two areas in which technology can be an ally to both health care organizations and providers while also supporting better outcomes for patients. Of course, the care continuum for a given patient frequently encompasses a wider network of caregivers, such as social workers, physical therapists and home health aides, that technology can also help integrate, but this piece focuses on the initial core of providers partnering around patient care.
When it comes to referrals, the prevailing strategy for clinicians is to to build a personal network of a few trusted providers with whom they have worked reliably over time. While this model fosters trusting relationships among providers, especially if they interact on a regular basis, it may not always be in the best interests of their patients. There are certainly benefits to providers being familiar with each other, but a clinician’s go-to provider for a given specialty may not be the best option for every patient. For example, the gastroenterologist one happens to know who performs colonoscopies exceptionally well may not be best suited to treating a patient with hepatic steatosis.
Providing the best care requires creating teams with provider expertise tailored to each individual’s clinical needs. Therefore, health care organizations maintain “rosters” of providers with different areas of expertise. These tools, also called provider directories, give organizations visibility into their provider networks and the skill sets of the providers therein.
A provider directory is a key part of the foundation for effective care coordination. When evaluating an organization’s directory, leaders should consider the following questions:
- Is there one central directory for the organization or are there multiple directories?
- How do providers and others involved in facilitating care (e.g., call center staff) access it?
- Is the directory static or updated on a regular basis?
- What level of detail does it contain about providers, clinical and otherwise? Does it give referring providers the information they need, including the depth and breadth of other providers’ clinical expertise, to make appropriate care decisions?
- What are the sources of information for the directory? When there are discrepancies, what’s the process for reconciling them?
- Are providers involved in contributing to or verifying their information?
- What are the organization’s processes for determining which providers should have which clinical areas of expertise listed? Who has ultimate accountability for the accuracy of the information?
- Are there vetting processes in place to validate that a given provider should (or shouldn’t) have a particular area of expertise listed?
- Do providers and others have a clear understanding of how to submit profile updates?
A provider directory has an essential role to play in enabling providers to look beyond their personal network for referrals. Thus, when looking to drive behavior changes and facilitate collaboration around patient care, organizations must take a close look at what information they make available to their providers.
Enabling communication within care teams
Ensuring that providers can build and understand their care teams is the first key step in facilitating integrated care teams and an area where technology can be a powerful enabler. After that, it’s equally important to enable providers to communicate with each other, stay informed about their patient’s care activity and close the loop on care events.
To maximize the effectiveness of integrated care teams, once clinicians have selected a provider they must be able to send referrals using a modern process. However, provider networks are continuously evolving; widespread variation in their infrastructure curtails the potential for electronic health records to enable this communication. Providers can sometimes find it a challenge to communicate efficiently, close the loop or understand what’s happening next for the patient. Did the patient show up? What did the provider determine? What’s the patient doing next? The inability to answer such questions easily is not only frustrating for providers but also hinders intervention by referring providers when necessary (e.g., if a patient doesn’t show up to an appointment). Similarly, it prevents the receiving providers from being able to ask questions or request more information without calling.
To be sure, there is still a place for phone-based communication among providers. In some instances, this is actually the best option, and technology shouldn’t aspire to replace it. Rather, technology should supplement these interactions when there is both an actual need and tangible benefit to deviating from traditional communication methods. To support integrated care teams, organizations need to look at where there are gaps appropriate for technology to fill, such as secure text messaging, e-consult solutions and referral mechanisms.
Making technology work for care teams
Building a truly coordinated and continuum-focused approach to patient care requires a fundamental shift in both how health care organizations think about constructing care teams and how they facilitate care coordination within them. Technology has a powerful role to play here, first by enabling organizations to enhance their provider directories and second by facilitating communication between often geographically dispersed providers. Both areas are critical; without the first, providers are limited in their ability to identify the right providers for each patient’s specific needs, and without the second they are limited in their ability to communicate effectively with the other providers involved in a patient’s care.
While both of these technology initiatives start at the organizational level, a proactive effort to include providers in their planning and implementation is essential for achieving the desired impact on care delivery. Technology can serve as a powerful enabler, but any effort to enhance how integrated teams form, collaborate and deliver care must involve the humans who will ultimately deliver that care. With appropriate technology, and the support of those who will use it, health care organizations can overcome key barriers to care coordination and help teams achieve better outcomes for their patients.
Health care providers are getting into the artificial intelligence game, and the technology is being used in myriad ways.
Just six months after El Camino Hospital in Silicon Valley implemented artificial intelligence technology, the rate at which patients suffered dangerous falls dropped 39 percent. The key, alongside additional fall prevention strategies, was a software program that predicts which individuals are most likely to fall by combing over electronic health records for risk factors and merging the data discovered there with real-time tracking of patients.
"Every time a patient pushes a call light or hits a bathroom or bed alarm, it's recorded," says Cheryl Reinking, chief nursing officer at El Camino. The software takes that information and compares the rate at which a patient is requesting assistance to data such as what surgeries he's had or which medications have been prescribed.
These data are all processed through "machine learning" – a form of artificial intelligence whereby computers take in new information and perform tasks based on it without being reprogrammed to do so. In this case, the program "learns" if a person may be more likely to fall based on his behavior and treatments. "Then it pushes an alert to the nurse saying 'your patient in room 2308 is at risk right now for falling,'" Reinking says, after which that individual might be moved closer to the nursing station or monitored via video.
The ability of computer systems to assume tasks for humans has improved efficiency in virtually every industry, from manufacturing to transportation. Now hospitals are getting into the game, deploying AI to take on challenges from diagnosing patients more quickly in the emergency room and streamlining communication between doctors to lessening the risk of complications so patients can go home sooner – and avoid being readmitted.
One big way in which patients will benefit directly is in AI's ability to help clinicians make diagnoses. IBM brought AI into the mainstream of medical care a few years back, when it offered its "Jeopardy!"-winning system Watson to cancer centers to help oncologists determine the best treatments for patients. Physicians can now plug patient diagnoses into IBM's Watson for Oncology and instantly receive treatment recommendations based on patient data and information pulled from reams of medical journal articles.
Since Watson's initial baby steps, AI has quickly demonstrated its potential to be a game-changer in many areas of health care. Other technology developers, for example, are focusing on software that can read CT scans and other medical images and then suggest the most likely diagnosis by reviewing similar images stored in patient databases. And these programs can accurately process these tasks far faster than human technicians. AI's potential is so promising that some experts predict it will eventually be every doctor's and nurse's go-to assistant.
New York University's Langone Medical Center is developing one AI system to predict which patients are likely to develop the dangerous condition sepsis and another that alerts doctors to cases of heart trouble. "If you're admitted to the ER for pneumonia, the people who are treating you may not think about the fact that you also have congestive heart failure," says Michael Cantor, an internist and associate professor in the hospital's departments of population health and medicine. The system will go through each patient's record when they're admitted and automatically alert cardiologists to anyone who has heart failure, so they can advise on how to avoid treatments that might exacerbate that condition.
Artificial intelligence is also being employed to improve efficiencies. Several hospitals are experimenting with technology to optimize schedules for surgeries and imaging tests by predicting how long each procedure that's scheduled in a particular day will take. Partners HealthCare, which includes Brigham and Women's and Massachusetts General hospitals in Boston, announced in May that it will work with General Electric over the next 10 years to incorporate AI into virtually every area of patient care, including developing applications to cut down on unnecessary biopsies and streamline administrative tasks for doctors.
These are all tasks that people traditionally do, but sometimes machines do them better, says Michael Williams, president of the University of North Texas Health Science Center. "Reducing ER wait times, improving surgical workflows – those are key to improving the patient experience, and AI has a real role to play."
If there's anything that's holding back the widespread adoption of AI in hospitals, it's nagging doubts that the technology will produce a good return on investment. A 2017 survey by HIMSS Analytics and Healthcare IT News found that 35 percent of health care organizations plan to adopt AI within two years, but 15 percent of respondents said they couldn't make a business case for doing so. And more than 20 percent said they thought the technology was still underdeveloped.
The field of AI in health care suffered a setback in February, when the University of Texas MD Anderson Cancer Center put its partnership with IBM on hold after an internal audit reported that the institution's effort to incorporate Watson into patient care ultimately failed to meet its goal. In an email, a spokeswoman for MD Anderson said the organization is constantly reviewing technologies that promise to improve cancer prevention and patient care, and that "while a variety of approaches have been examined, a final approach using this technology to benefit patients has not been determined at this time."
Rob Merkel, general manager of oncology and genomics for Watson Health, says the company is making headway in the market with Watson for Oncology, which IBM developed with Memorial Sloan Kettering Cancer Center in New York. And he cites research the firm did with MD Anderson that he believes shows Watson's potential. "We demonstrated 95 percent concordance with what Watson would recommend as a treatment option versus what an MD Anderson physician would recommend," he says.
So could AI someday even substitute for doctors? Peter Slavin, president of Mass General, believes people will always be essential to delivering high-quality care – but that machines will become increasingly vital to making that care better. Improvements in computing power and the ability of computer programs to emulate neural networks in the brain unlock enormous possibilities for the use of AI in medicine, Slavin says. "We haven't really even begun to see its impact."
With opioid addiction officially a public health emergency in the United States, it’s more important than ever that physicians and other clinicians carefully document a patient’s opioid use in the electronic health record.
To help providers better document the use and abuse of opioids, the American Health Information Management Association (AHIMA) has created an opioid addiction documentation tip sheet that gives examples of proper documentation that complies with the seven characteristics of high-quality clinical documentation. Those factors include providing clear, precise, complete information.
AHIMA spokesperson Mary Jo Contino said proper documentation and EHR interoperability is often overlooked as a tactic to help reverse the country’s opioid epidemic. Fewer than 30% of health system EHRs are fully interoperable, and less than 20% actually use data transferred from another provider, according to a new study.
It’s important that physicians and other healthcare providers accurately record information in the EHR when an individual using or abusing opioids visits their office. Without national communication standards for health information exchange, that documentation is often not shared among healthcare system facilities or across state lines, allowing people with addictions to seek opioids from multiple physicians.
Meanwhile, Prescription Drug Monitoring Programs (PDMPs) are gaining traction as opioid overdose deaths have skyrocketed. Last month, the President's Commission on Combating Drug Addiction and the Opioid Crisis recommended state and federal PDMPs be interoperable within 12 months.
Last month, President Donald Trump declared the opioid epidemic a national public health emergency. AHIMA says high-quality clinical documentation will guarantee that the data which drives research and education about opioid addiction is based on correct information.
Betty Rockendorf, MS, RHIA, CHPS, CHTS-IM
The world of healthcare and health information management (HIM) is quickly moving to meet the demand of analyzing and making sense of all the data that is collected—and, ultimately, turning it into useful information.
Data is defined as “facts and statistics collected together for reference or analysis.” Information is “facts provided or learned about something or someone, ‘a vital piece of information.’” The question of how information governance and data governance differ from each other is addressed in the Information Governance FAQs on AHIMA’s website:
Data governance “is primarily concerned with policies and strategies that address the creation and use of granular data as inputs into a system,” i.e., master data management, metadata management, data models and architecture.
Information Governance is concerned with “lifecycle management of this data and information, including its use, protection, and preservation,” i.e. health information exchange, compliance audits, e-discovery and retention of records.
So the two are related and data governance is actually a domain within Information Governance.
HIM professionals are tasked with improving the consistency, reliability, and usability of data assets while optimizing electronic health record (EHR) interfaces. This is necessary to eliminate duplicate records, to address problematic workarounds, and to maintain patient safety. If the data is incorrect (or missing completely) in the case of allergies, current medications, past procedures, and health conditions of a patient, it can be detrimental to the course of treatment and care of the patient.
Additionally, providers are now trying to pull useful information out of the data in their EHRs to support the goals of healthier patients, lower costs, improved performance, and increased staff and patient satisfaction rates.
Merida Johns defines Big Data as “the concept of large volumes of complex and diverse data.” We must utilize our Big Data assets and extract business and clinical value from them. Strong information governance and data governance practices will allow healthcare organizations to maximize the value of their data and information to use in order to meet strategic goals and other requirements. Some of the top challenges facing organizations—and thus opportunities for HIM professionals to step up and demonstrate their value to the organizations—who wish to begin Big Data analytics, according to an article by Jennifer Bresnick in HealthITAnalytics, include:
- Capture of data
- Cleansing of data
- Storage of data
- Security of data
- Stewardship of data
- Querying of data
- Reporting of data
- Visualization of data
- Updating of datasets
- Sharing data
It’s a big list of challenges and opportunities, but “In order to develop a big data exchange ecosystem that connects all members of the care continuum with trustworthy, timely, and meaningful information, providers will need to overcome every challenge on this list,” according to Bresnick.
What are some first steps that we can take? We need to gain the support and buy-in of our organizational leaders. HIM professionals should be strongly advocating within their organizations for a data governance strategy. Get the C-suite involved and make sure that everyone on the corporate ladder understands the importance. As Bresnick writes in another HealthITAnalytics article: “ignoring the role of data governance in the big data environment may be penny wise, pound foolish. Without robust, accurate, timely, clean, and complete data, healthcare organizations will not be able to move beyond the basics of record keeping and develop the analytics competencies that will become vital survival skills in the emerging world of value-based care.”
In a 2013 report from Kaiser Permanente, the University of Pennsylvania, and several public health institutes researchers strongly recommended the creation of “a set of guiding data governance principles that fit the mission, vision, and values of the particular provider,” according to Bresnick. It was further recommended to start with specific policies and procedures about data collection, paying particular attention to:
- How people work together
- Management of cross-functional conflicts
- Decision-making and rights
- Management of change
- Resolution of issues
- Making and enforcing rules
- Management of cost and complexity
- Creating value
Next, communicate to everyone in the organization, being sure to explain, give details, answer questions, and get buy-in for improvement activities that are planned. After the data governance leadership team has established a strong data governance vision and has gotten everyone on board, start with prioritizing projects that need to be improved on the data level. Take the time to train staff within the organization who are charged with creating, using, and sharing data. This could include areas such as clinical documentation improvement or patient registration.
The benefits for the healthcare organization will be seen on the financial side as well as quality side. And the goal, of course, would be improved patient outcomes. This project is not a one-and-done endeavor. Developing and sustaining the program is an ongoing process. To be sure, continued monitoring needs to exist, as well as continued improvements and reassessments. The organization and the data governance leadership team will need to continue training end-users, identifying roles as it relates to data governance activities, providing reminders about data integrity, and maintaining sound data entry practices. Audits should also be conducted within the organization to maintain high data quality.
As Bresnick writes, “These activities will ensure that healthcare providers are prepared to utilize their growing big data resources for generating actionable insights, and that they are being mindful of patient safety and care quality as they optimize their assets for the future of value-based care.” We need to be sure our information at the data level is accurate, reliable, and timely as we use it to make important business and clinical decisions. Data governance best practices are imperative for a successful information governance program and keeping up with the current in the Big Data era.